Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5455 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6517. Min Range: -5.6517

Max Act: 5.6517. Min Act: -0.0000

Data Index: 758193 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 5.6517. Min Range: -5.6517

Max Act: 5.1506. Min Act: -0.0000

Data Index: 1060111 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 5.6517. Min Range: -5.6517

Max Act: 5.3444. Min Act: -0.0000

Data Index: 849072 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 5.6517. Min Range: -5.6517

Max Act: 5.1034. Min Act: -0.0000

Data Index: 406016 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.6567. Min Act: -0.0000

Data Index: 762625 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.9285. Min Act: -0.0000

Data Index: 477825 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.9481. Min Act: -0.0000

Data Index: 1359688 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.3558. Min Act: -0.0000

Data Index: 21476 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.5642. Min Act: -0.0000

Data Index: 426357 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.7908. Min Act: -0.0000

Data Index: 1048277 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.3398. Min Act: -0.0000

Data Index: 1255702 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.7158. Min Act: -0.0000

Data Index: 215032 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.4522. Min Act: -0.0000

Data Index: 1077986 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.4293. Min Act: -0.0000

Data Index: 399892 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.1809. Min Act: -0.0000

Data Index: 841276 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.2516. Min Act: -0.0000

Data Index: 705153 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.1837. Min Act: -0.0000

Data Index: 882817 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.3730. Min Act: -0.0000

Data Index: 1267047 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.0084. Min Act: -0.0000

Data Index: 737265 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 5.6517. Min Range: -5.6517

Max Act: 4.3624. Min Act: -0.0000

Data Index: 972801 (C4 (Web Text))

Max Activating Token Index: 846